NVIDIA’s Axolotl3D unifies 3D completion, editing, and extraction in one model
NVIDIA Developer · youtube · 2026-07-29
Axolotl3D unifies several 3D tasks in one model
NVIDIA Research introduced Axolotl3D, a unified 3D generation model that can complete objects from partial observations such as images, visibility masks, and point clouds.
- Handles multi-view image-to-3D, occlusion completion, local shape editing, and object extraction from Gaussian Splat scenes in a single model.
- The model is trained by simulating diverse partial observations from large-scale 3D data.
- The work has been accepted to ECCV 2026.
The project page and paper are both public.
Related event: NVIDIA Introduces Axolotl3D for Unified 3D Completion(2 posts)→
More from Multimodal
- Google Gemini Omni Flash is used to make short videos at about 90 credits each — iamaliveix · 2026-07-29
- Microsoft removes Mage Flow and points to a more efficient Qwen-VL-class encoder — Dante_77A · 2026-07-29
- Opus 5 users are building full games, FPS prototypes, and 3D scenes in one shot — eyishazyer · 2026-07-29
- Seedance 2.0 prompt turns text-to-video into a chaotic bodycam street scene — techhalla · 2026-07-29
- A burger-cooking AI demo splits viewers between detail accuracy and ad-like polish — victor_explore · 2026-07-29
- SCAIL 2 survives character swaps, object permanence, and physics tests better than expected — blackmixture · 2026-07-29